© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2801
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming logic and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, tags, or commands

    np_acts-logits-general · gemini-2.0-flash

    automatic activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.50
    %</
    -0.39
    enfance
    -0.39
     רבים
    -0.37
    FieldDescriptor
    -0.37
    utives
    -0.37
     längre
    -0.36
     pudesse
    -0.36
    емость
    -0.36
    アプローチ
    -0.35
    POSITIVE LOGITS
     automatically
    0.86
    automatically
    0.62
     surla
    0.60
     AUTOMATIC
    0.57
     automaticamente
    0.56
     автоматически
    0.54
     automatic
    0.54
     Automatically
    0.53
     immediately
    0.53
     AssemblyCompany
    0.52
    Activations Density 0.841%

    No Known Activations